agent-backbone 0.3.0__tar.gz → 0.4.0__tar.gz

agent_backbone-0.4.0/PKG-INFO

@@ -0,0 +1,298 @@
+Metadata-Version: 2.5
+Name: agent-backbone
+Version: 0.4.0
+Summary: Bring agents across AI CLIs and projects into one personal team, with communication, coordination and continuity.
+Project-URL: Homepage, https://github.com/eandualem/agent-backbone
+Project-URL: Documentation, https://github.com/eandualem/agent-backbone/blob/main/docs/INDEX.md
+Project-URL: Source, https://github.com/eandualem/agent-backbone
+Project-URL: Issues, https://github.com/eandualem/agent-backbone/issues
+License: MIT
+License-File: LICENSE
+Keywords: agents,claude-code,codex,github,orchestration,telegram,tmux
+Classifier: Development Status :: 3 - Alpha
+Classifier: Environment :: Console
+Classifier: Intended Audience :: Developers
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Operating System :: MacOS
+Classifier: Operating System :: POSIX :: Linux
+Classifier: Programming Language :: Python :: 3 :: Only
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: 3.13
+Classifier: Topic :: Software Development
+Requires-Python: >=3.11
+Requires-Dist: aiosqlite>=0.20
+Requires-Dist: alembic>=1.13
+Requires-Dist: cryptography>=44.0
+Requires-Dist: fastapi>=0.115
+Requires-Dist: httpx>=0.27
+Requires-Dist: ironcalc==0.9.1
+Requires-Dist: pydantic>=2.0
+Requires-Dist: python-dotenv>=1.0
+Requires-Dist: python-engineio>=4.13.5
+Requires-Dist: python-socketio>=5.16.4
+Requires-Dist: python-telegram-bot>=21.0
+Requires-Dist: rich>=14.1
+Requires-Dist: sqlalchemy[asyncio]>=2.0
+Requires-Dist: uvicorn[standard]>=0.32
+Provides-Extra: postgres
+Requires-Dist: asyncpg>=0.29; extra == 'postgres'
+Description-Content-Type: text/markdown
+
+<div align="center">
+
+<img src="https://raw.githubusercontent.com/eandualem/agent-backbone/main/docs/media/banner.png" alt="agent-backbone: your terminal agents, working as a team" width="720">
+
+**Agents across different AI CLIs and projects, working as one personal team.**<br>
+Communication, coordination and continuity for Claude Code, Codex and OpenCode.<br>
+Develop specialists whose experience carries into your next project.
+
+[![PyPI](https://img.shields.io/pypi/v/agent-backbone)](https://pypi.org/project/agent-backbone/)
+[![Python](https://img.shields.io/pypi/pyversions/agent-backbone)](https://pypi.org/project/agent-backbone/)
+[![CI](https://github.com/eandualem/agent-backbone/actions/workflows/ci.yml/badge.svg)](https://github.com/eandualem/agent-backbone/actions/workflows/ci.yml)
+[![Downloads](https://img.shields.io/pypi/dm/agent-backbone)](https://pypistats.org/packages/agent-backbone)
+[![License: MIT](https://img.shields.io/badge/license-MIT-blue)](https://github.com/eandualem/agent-backbone/blob/main/LICENSE)
+
+[Watch](#watch) · [Quick start](#quick-start) · [Why Backbone](#why-backbone) · [Docs](https://github.com/eandualem/agent-backbone/blob/main/docs/INDEX.md) · [Security](https://github.com/eandualem/agent-backbone/blob/main/docs/security.md)
+
+</div>
+
+## Watch
+
+<a href="https://youtu.be/3gOH3t3woXM"><img src="https://raw.githubusercontent.com/eandualem/agent-backbone/main/docs/media/film-overview.jpg" width="49%" alt="Watch the agent-backbone overview, 1 minute 23 seconds"></a>
+
+<a href="https://youtu.be/yKV8RNgqRsE"><img src="https://raw.githubusercontent.com/eandualem/agent-backbone/main/docs/media/film-why-backbone.jpg" width="49%" alt="Watch Why Backbone, 2 minutes 23 seconds"></a>
+
+[Overview (1:23)](https://youtu.be/3gOH3t3woXM) · [Why Backbone (2:23)](https://youtu.be/yKV8RNgqRsE) · [YouTube playlist](https://www.youtube.com/playlist?list=PLMq17WKA4Z88)
+
+Both films have English captions. [Read the film guide](https://github.com/eandualem/agent-backbone/blob/main/docs/media/films.md).
+
+## Why Backbone
+
+Agent Backbone brings agents across different AI CLIs and projects into one
+personal team. It provides the communication, coordination and continuity they
+need to work together, with working practices you can shape. Through that
+collaboration, retained lessons and feedback, specialists can develop expertise,
+share discoveries and refine their judgment, so each new project can benefit
+from the experience they have built.
+
+Your agents use the logins you already have. Core use needs no setup in your
+repositories. [Starter practices](https://github.com/eandualem/agent-backbone/blob/main/docs/team.md) help the team collaborate,
+preserve useful reasoning and learn from feedback; you can edit or remove them.
+
+<table>
+<tr>
+<td width="50%" valign="top">
+
+**Never typed into a busy agent**<br>
+Agents reach each other by name. When the recipient is working or waiting
+for you, the message is queued and delivered when the agent is ready, marked
+with who sent it. Ordinary messages expire after 30 minutes by default, and
+the sender is told.
+
+</td>
+<td width="50%" valign="top">
+
+**No setup in your repositories**<br>
+An agent is a folder and the CLI you choose, and the folder is its name.
+Core use adds no configuration files, task schemas or commits to your
+projects.
+
+</td>
+</tr>
+<tr>
+<td valign="top">
+
+**GitHub Issues are the task list**<br>
+In a repository worker owns or watches, label an issue `for:worker` and it
+lands in worker's queue, one at a time.
+To hand work on, an agent opens an issue for another. The issue stays as the
+record.
+
+</td>
+<td valign="top">
+
+**Mix CLIs in one team**<br>
+Claude Code, Codex and OpenCode agents work side by side, and a swarm puts a
+coordinator and helpers on different CLIs on one branch. A second model can
+review the change.
+
+</td>
+</tr>
+<tr>
+<td valign="top">
+
+**In the loop from anywhere**<br>
+Watch any agent, step into its terminal, or answer from your phone. With
+[Telegram set up](https://github.com/eandualem/agent-backbone/blob/main/docs/telegram.md#one-topic-per-agent) in a group with
+topics, every agent outside a swarm gets its own topic, with Allow and Deny
+on permission prompts.
+
+</td>
+<td valign="top">
+
+**State you can check**<br>
+Backbone tracks whether each agent is idle, working or waiting for a person,
+and shows the evidence behind every reading. Your agents decide the work.
+
+</td>
+</tr>
+</table>
+
+New sessions are briefed on these tools, so you can ask any agent to set up
+the team you need: an agent per repository, skills and rules shared by tag,
+specialists on request.
+
+For example, a README specialist can retain why an explanation worked, consult
+with another repository's agent and adapt that lesson to its readers. The team
+must record, test and revise its understanding; a role name or stored conversation
+alone does not make it more capable. [Try that collaboration](https://github.com/eandualem/agent-backbone/blob/main/docs/team.md#try-a-readme-collaboration).
+
+## Use a desktop workspace
+
+Agent Interface provides a native desktop for Backbone: terminals alongside
+team, activity, usage, skills and policy views. Its **Reports & updates** view brings together progress reports, saved
+answers and Documents. Rich HTML Documents currently render on macOS.
+Connect it to a running Backbone.
+
+## Quick start
+
+**Let your agent do it.** Open the coding agent you already use and say:
+
+```text
+Install agent-backbone with uv tool install agent-backbone,
+then run backbone help setup and follow it.
+```
+
+The setup playbook is written for agents: each step ends with a check and
+says when it needs you, for your accounts and secrets. If your agent's CLI
+refuses a step on its own (Claude Code's auto mode can refuse
+`backbone init`), switch it to asking before each step (Shift+Tab in
+Claude Code) and approve them.
+
+**Or by hand.** You need macOS or Linux, Python 3.11+, tmux,
+[uv](https://docs.astral.sh/uv/) (or pipx), and an agent CLI installed and
+signed in.
+
+```bash
+uv tool install agent-backbone
+backbone init
+backbone service install           # start now and at login
+backbone doctor                    # check dependencies and API access
+```
+
+For a **new installation**, read `backbone docs team` and select its starter
+practices before launching agents:
+
+```bash
+backbone templates use starter-collaboration starter-continuity starter-learning
+```
+
+On an existing installation, first inspect assignments with `backbone templates use`.
+Selection replaces the global list, so keep existing choices or use a tag.
+You can customize or remove any starter.
+
+Then, from a repository you want an agent to work in:
+
+```bash
+cd ~/code/app
+backbone agent start --runtime claude   # or --runtime codex, --runtime opencode
+backbone tell app "Summarise what this repository does in three sentences."
+backbone agent attach app               # read its reply; Ctrl-b d detaches
+```
+
+The folder supplies the agent name. If startup reports a prompt or a timeout,
+`backbone agent inspect app` shows what needs attention. `tell` reports
+whether the message was delivered or queued; delivery does not mean the agent
+has finished answering. A queued message waits until the agent is ready, up
+to 30 minutes by default, so do not resend a message the queue accepted. If
+`backbone` is not on your PATH, run `uv tool update-shell` and open a new
+terminal. In a container without a login service, use `backbone up --detach`.
+`ab` is a short alias; on macOS, use `backbone` if Apache Bench shadows it.
+
+[Getting started](https://github.com/eandualem/agent-backbone/blob/main/docs/getting-started.md) walks through a second agent,
+GitHub and Telegram. [Develop your team](https://github.com/eandualem/agent-backbone/blob/main/docs/team.md) follows a specialist's
+experience into another project. [Quick usage](https://github.com/eandualem/agent-backbone/blob/main/USAGE.md) is the everyday command guide.
+
+## Built to be relied on
+
+- **One delivery gate.** Everything typed into an agent's terminal passes the
+  same readiness check. Busy agents are never interrupted, and every message
+  carries where it came from.
+- **The same result on every required CLI.** A capability ships only when it
+  works the same in Claude Code, Codex and OpenCode, checked by the same
+  behaviour test on each. The [runtime capability table](https://github.com/eandualem/agent-backbone/blob/main/docs/runtime-capabilities.md)
+  and `backbone doctor` read one contract, and gaps are listed, not hidden.
+- **More than 3,500 tests,** run on every change with no network, models or
+  services.
+- **Built with itself.** Backbone is developed by agents running inside a
+  Backbone in daily use. The films in this README were made the same way.
+- **An honest security model.** One trusted user on one machine, an API on
+  localhost, and a clear account of what agents can reach. Read
+  [Security](https://github.com/eandualem/agent-backbone/blob/main/docs/security.md) before granting access.
+
+Backbone is not an agent framework: it calls no models and needs no model API
+keys. It is not a workflow engine or a dashboard either. It gives your
+agents names, safe messages and evidence, and leaves the work to them.
+
+## Works with
+
+| CLI | Support |
+|---|---|
+| Claude Code, Codex, OpenCode | Required set: a capability ships only when it works on all three, and any open gap is tracked as a defect |
+| Gemini CLI, Deep Code, Aider | Supported on demand; each gap is listed in the [capability table](https://github.com/eandualem/agent-backbone/blob/main/docs/runtime-capabilities.md) |
+
+## Going further
+
+- [Develop your team](https://github.com/eandualem/agent-backbone/blob/main/docs/team.md): choose starting practices, collaborate with
+  a specialist and carry useful lessons into another project.
+- [GitHub](https://github.com/eandualem/agent-backbone/blob/main/docs/github.md): route issues and review notifications, starting with
+  token-based polling. [GitHub App setup](https://github.com/eandualem/agent-backbone/blob/main/docs/github-app-setup.md) adds webhooks.
+- [Swarms](https://github.com/eandualem/agent-backbone/blob/main/docs/swarms.md): put several specialists on one task.
+- [Skills](https://github.com/eandualem/agent-backbone/blob/main/docs/skills.md): keep one copy of each skill, tag it, and every agent
+  with that tag finds it in its own CLI.
+- [Telegram](https://github.com/eandualem/agent-backbone/blob/main/docs/telegram.md): send messages and read reports from your phone.
+- [Token usage](https://github.com/eandualem/agent-backbone/blob/main/docs/token-usage.md): tokens by agent, conversation and model.
+- [Saved answers](https://github.com/eandualem/agent-backbone/blob/main/docs/responses.md): return to a question, its answer and next action.
+- [Documents](https://github.com/eandualem/agent-backbone/blob/main/docs/documents.md): keep detailed explanations and interactive HTML
+  reports available beyond the conversation, with retained correction history.
+- [API](https://github.com/eandualem/agent-backbone/blob/main/docs/api.md): build a dashboard or automation; Backbone ships no UI.
+- [Runtime support and limits](https://github.com/eandualem/agent-backbone/blob/main/docs/status-and-roadmap.md): checked capabilities,
+  unsupported environments and known limitations.
+- [How it works](https://github.com/eandualem/agent-backbone/blob/main/docs/how-it-works.md): state detection, delivery and routing.
+
+The [documentation index](https://github.com/eandualem/agent-backbone/blob/main/docs/INDEX.md) covers configuration, diagnostics
+and the remaining references. Installed copies are available through
+`backbone docs`; `backbone help` contains short agent playbooks.
+
+## Security model
+
+Backbone runs as one trusted OS user on one machine. Agents are not isolated
+from each other. The API binds to localhost by default and uses one full-admin
+key; local sessions can read that key through the CLI. Backbone keeps its
+control-plane secrets out of launched environments, but this is not a filesystem
+security boundary. Read [Security](https://github.com/eandualem/agent-backbone/blob/main/docs/security.md) before granting access or
+exposing the API.
+
+## Development
+
+```bash
+git clone https://github.com/eandualem/agent-backbone
+cd agent-backbone
+make install
+make check
+BACKBONE_DATA_DIR=/tmp/backbone-dev make dev
+```
+
+`make dev` runs on its own tmux server, so its agents stay apart from your own
+tmux sessions and from a real backbone's agents. Run CLI commands for it from
+a terminal outside tmux with the same settings, for example
+`TMUX_TMPDIR=/tmp/backbone-dev-tmux-$(id -u) BACKBONE_DATA_DIR=/tmp/backbone-dev uv run backbone agent attach NAME`.
+`agent attach`, and agent commands run while `make dev` is stopped, use tmux
+directly.
+
+See [Contributing](https://github.com/eandualem/agent-backbone/blob/main/CONTRIBUTING.md) for branches, checks and releases.
+
+## License
+
+[MIT](https://github.com/eandualem/agent-backbone/blob/main/LICENSE).

agent_backbone-0.3.0/PKG-INFO → agent_backbone-0.4.0/README.md

@@ -1,49 +1,10 @@
-Metadata-Version: 2.5
-Name: agent-backbone
-Version: 0.3.0
-Summary: Local control plane for terminal AI agents: run them, message them, coordinate them through GitHub Issues, reach them from Telegram.
-Project-URL: Homepage, https://github.com/eandualem/agent-backbone
-Project-URL: Documentation, https://github.com/eandualem/agent-backbone/blob/main/docs/INDEX.md
-Project-URL: Source, https://github.com/eandualem/agent-backbone
-Project-URL: Issues, https://github.com/eandualem/agent-backbone/issues
-License: MIT
-License-File: LICENSE
-Keywords: agents,claude-code,codex,github,orchestration,telegram,tmux
-Classifier: Development Status :: 3 - Alpha
-Classifier: Environment :: Console
-Classifier: Intended Audience :: Developers
-Classifier: License :: OSI Approved :: MIT License
-Classifier: Operating System :: MacOS
-Classifier: Operating System :: POSIX :: Linux
-Classifier: Programming Language :: Python :: 3 :: Only
-Classifier: Programming Language :: Python :: 3.11
-Classifier: Programming Language :: Python :: 3.12
-Classifier: Programming Language :: Python :: 3.13
-Classifier: Topic :: Software Development
-Requires-Python: >=3.11
-Requires-Dist: aiosqlite>=0.20
-Requires-Dist: alembic>=1.13
-Requires-Dist: cryptography>=44.0
-Requires-Dist: fastapi>=0.115
-Requires-Dist: httpx>=0.27
-Requires-Dist: pydantic>=2.0
-Requires-Dist: python-dotenv>=1.0
-Requires-Dist: python-socketio>=5.11
-Requires-Dist: python-telegram-bot>=21.0
-Requires-Dist: rich>=14.1
-Requires-Dist: sqlalchemy[asyncio]>=2.0
-Requires-Dist: uvicorn[standard]>=0.32
-Provides-Extra: postgres
-Requires-Dist: asyncpg>=0.29; extra == 'postgres'
-Description-Content-Type: text/markdown
-
 <div align="center">
 
 <img src="docs/media/banner.png" alt="agent-backbone: your terminal agents, working as a team" width="720">
 
-**Claude Code, Codex and OpenCode, working as one team on your machine.**<br>
-Agents message each other by name, take work from GitHub Issues and reach you on your phone.<br>
-They use the logins you already have, and core use needs no setup in your repositories.
+**Agents across different AI CLIs and projects, working as one personal team.**<br>
+Communication, coordination and continuity for Claude Code, Codex and OpenCode.<br>
+Develop specialists whose experience carries into your next project.
 
 [![PyPI](https://img.shields.io/pypi/v/agent-backbone)](https://pypi.org/project/agent-backbone/)
 [![Python](https://img.shields.io/pypi/pyversions/agent-backbone)](https://pypi.org/project/agent-backbone/)
@@ -59,16 +20,24 @@ They use the logins you already have, and core use needs no setup in your reposi
 
 https://github.com/user-attachments/assets/695a6096-4196-4115-911c-a0043d632088
 
-<p align="center"><sub>The overview, 1:23, captioned. Unmute for the narration.</sub></p>
+https://github.com/user-attachments/assets/4218fdbe-e581-49bd-879f-288d41c9f72f
+
+[Overview (1:23)](https://youtu.be/3gOH3t3woXM) · [Why Backbone (2:23)](https://youtu.be/yKV8RNgqRsE) · [YouTube playlist](https://www.youtube.com/playlist?list=PLMq17WKA4Z88)
 
-<p align="center"><b>Up next</b>&nbsp;&nbsp;›<br>
-<a href="docs/media/films.md#why-backbone"><img src="docs/media/film-why-backbone.jpg" width="49%" alt="Why Backbone, 2 minutes 23: from 'set up Backbone for me' to a team on three CLIs"></a>
-</p>
+Both films have English captions. [Read the film guide](docs/media/films.md).
 
 ## Why Backbone
 
-You already run coding agents in your terminal. Each one works alone, and you
-carry every message between them. Backbone turns them into a team.
+Agent Backbone brings agents across different AI CLIs and projects into one
+personal team. It provides the communication, coordination and continuity they
+need to work together, with working practices you can shape. Through that
+collaboration, retained lessons and feedback, specialists can develop expertise,
+share discoveries and refine their judgment, so each new project can benefit
+from the experience they have built.
+
+Your agents use the logins you already have. Core use needs no setup in your
+repositories. [Starter practices](docs/team.md) help the team collaborate,
+preserve useful reasoning and learn from feedback; you can edit or remove them.
 
 <table>
 <tr>
@@ -133,6 +102,18 @@ New sessions are briefed on these tools, so you can ask any agent to set up
 the team you need: an agent per repository, skills and rules shared by tag,
 specialists on request.
 
+For example, a README specialist can retain why an explanation worked, consult
+with another repository's agent and adapt that lesson to its readers. The team
+must record, test and revise its understanding; a role name or stored conversation
+alone does not make it more capable. [Try that collaboration](docs/team.md#try-a-readme-collaboration).
+
+## Use a desktop workspace
+
+Agent Interface provides a native desktop for Backbone: terminals alongside
+team, activity, usage, skills and policy views. Its **Reports & updates** view brings together progress reports, saved
+answers and Documents. Rich HTML Documents currently render on macOS.
+Connect it to a running Backbone.
+
 ## Quick start
 
 **Let your agent do it.** Open the coding agent you already use and say:
@@ -143,7 +124,10 @@ then run backbone help setup and follow it.
 ```
 
 The setup playbook is written for agents: each step ends with a check and
-says when it needs you, for your accounts and secrets.
+says when it needs you, for your accounts and secrets. If your agent's CLI
+refuses a step on its own (Claude Code's auto mode can refuse
+`backbone init`), switch it to asking before each step (Shift+Tab in
+Claude Code) and approve them.
 
 **Or by hand.** You need macOS or Linux, Python 3.11+, tmux,
 [uv](https://docs.astral.sh/uv/) (or pipx), and an agent CLI installed and
@@ -156,6 +140,17 @@ backbone service install           # start now and at login
 backbone doctor                    # check dependencies and API access
 ```
 
+For a **new installation**, read `backbone docs team` and select its starter
+practices before launching agents:
+
+```bash
+backbone templates use starter-collaboration starter-continuity starter-learning
+```
+
+On an existing installation, first inspect assignments with `backbone templates use`.
+Selection replaces the global list, so keep existing choices or use a tag.
+You can customize or remove any starter.
+
 Then, from a repository you want an agent to work in:
 
 ```bash
@@ -175,7 +170,8 @@ terminal. In a container without a login service, use `backbone up --detach`.
 `ab` is a short alias; on macOS, use `backbone` if Apache Bench shadows it.
 
 [Getting started](docs/getting-started.md) walks through a second agent,
-GitHub and Telegram. [Quick usage](USAGE.md) is the everyday command guide.
+GitHub and Telegram. [Develop your team](docs/team.md) follows a specialist's
+experience into another project. [Quick usage](USAGE.md) is the everyday command guide.
 
 ## Built to be relied on
 
@@ -207,6 +203,8 @@ agents names, safe messages and evidence, and leaves the work to them.
 
 ## Going further
 
+- [Develop your team](docs/team.md): choose starting practices, collaborate with
+  a specialist and carry useful lessons into another project.
 - [GitHub](docs/github.md): route issues and review notifications, starting with
   token-based polling. [GitHub App setup](docs/github-app-setup.md) adds webhooks.
 - [Swarms](docs/swarms.md): put several specialists on one task.
@@ -214,6 +212,9 @@ agents names, safe messages and evidence, and leaves the work to them.
   with that tag finds it in its own CLI.
 - [Telegram](docs/telegram.md): send messages and read reports from your phone.
 - [Token usage](docs/token-usage.md): tokens by agent, conversation and model.
+- [Saved answers](docs/responses.md): return to a question, its answer and next action.
+- [Documents](docs/documents.md): keep detailed explanations and interactive HTML
+  reports available beyond the conversation, with retained correction history.
 - [API](docs/api.md): build a dashboard or automation; Backbone ships no UI.
 - [Runtime support and limits](docs/status-and-roadmap.md): checked capabilities,
   unsupported environments and known limitations.

{agent_backbone-0.3.0 → agent_backbone-0.4.0}/USAGE.md

@@ -19,6 +19,19 @@ backbone status
 Without a login service (for example, in a container), use `backbone up --detach`.
 Run `backbone doctor` if setup needs attention.
 
+The starter policies teach collaboration, continuity and learning from feedback.
+For a **new installation**, read `backbone docs team` and select them before
+starting agents:
+
+```bash
+backbone templates use starter-collaboration starter-continuity starter-learning
+```
+
+On an existing installation, inspect assignments with `backbone templates use`
+first: selecting policies replaces the global list. Preserve the choices you
+still want. The team guide explains customization and a specialist collaboration
+across projects.
+
 ## Work with an agent
 
 ```bash
@@ -37,6 +50,28 @@ An already running agent stays running. Starting from its directory also finds
 its registered name. Choose `--runtime` and `--model` explicitly to change them;
 changing CLI without a model clears the old CLI's model setting.
 
+## Find a saved answer
+
+`backbone responses --agent app` lists an agent's saved questions, answers and
+actions. `backbone responses show ID` reads one in full. Agents publish explicitly
+with `backbone respond --file answer.json` while continuing their work; the full
+answer is also queued to their Telegram topic. See [Responses](docs/responses.md).
+
+## Find a saved document
+
+```bash
+backbone documents --agent app
+backbone documents show ID                 # metadata for a revision from the list
+backbone documents show ID --output report.html
+```
+
+Documents retain detailed explanations, analyses and interactive HTML reports.
+Open them in Agent Interface's **Reports & updates** view on macOS, or export
+a revision to a file. Agents publish deliberately with
+`backbone documents publish --file report.html --title "Report"`; publication
+stores it without sending a notification or creating a public page.
+See [Documents](docs/documents.md) for validation, corrections and limits.
+
 ## Read agent progress
 
 ```bash

{agent_backbone-0.3.0 → agent_backbone-0.4.0}/docs/INDEX.md

@@ -9,13 +9,19 @@ branch or tag you are viewing. Relative links keep you on that same revision.
 ## 1. Get started
 
 1. [Getting started](getting-started.md) — install, start agents and send a message.
-2. [Concepts](concepts.md) — names, runtimes, states and delivery conditions.
-3. [CLI reference](cli.md) — start, resume, attach, rename and configure agents.
+2. [Develop your team](team.md) — editable starting practices and expertise shared across projects.
+3. [Concepts](concepts.md) — names, runtimes, states and delivery conditions.
+4. [CLI reference](cli.md) — start, resume, attach, rename and configure agents.
 
 ## 2. Run your team
 
 - [Token usage](token-usage.md) — per-agent CLI sessions, model tokens and optional API estimates.
 - [Report audio](report-audio.md) — optional local read-aloud in Telegram.
+- [Saved answers](responses.md) — question, answer and action, retrievable while work continues.
+- [Sheets](sheets.md) — editable workbooks, formulas, immutable revisions and contextual feedback.
+- [Current plans](current-plans.md) — short agent-authored checklists and contextual questions.
+- [Documents](documents.md) — retained HTML with immutable revisions and metadata discovery.
+- [Conversations](conversations.md) — ask about a Document, Response or report and read the reply beside it.
 - [Progress reports](reports.md) — goals, progress, blockers and next steps.
 - [Instruction templates](templates.md) — edit base, role and tag instructions.
 - [Skills](skills.md) — one shared store of skills, given to agents by tag.
@@ -48,3 +54,5 @@ branch or tag you are viewing. Relative links keep you on that same revision.
 [Help](../help/) contains short playbooks agents request with `backbone help`.
 [Templates](../templates/) contains instructions injected at launch.
 [Media](media/) contains documentation illustrations and recordings.
+
+- [Installer setup](installer-setup.md) — finite operator initialization, first-agent creation and retry receipts.